scholarly journals Parkinson’s disease: deep learning with a parameter-weighted structural connectome matrix for diagnosis and neural circuit disorder investigation

2021 ◽  
Author(s):  
Koichiro Yasaka ◽  
Koji Kamagata ◽  
Takashi Ogawa ◽  
Taku Hatano ◽  
Haruka Takeshige-Amano ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Basal Ganglia ◽  
Neural Circuit ◽  
Characteristic Curve ◽  
Diffusion Kurtosis Imaging ◽  
Healthy Controls ◽  
Structural Connectome ◽  
Learning Technique

Abstract Purpose To investigate whether Parkinson’s disease (PD) can be differentiated from healthy controls and to identify neural circuit disorders in PD by applying a deep learning technique to parameter-weighted and number of streamlines (NOS)–based structural connectome matrices calculated from diffusion-weighted MRI. Methods In this prospective study, 115 PD patients and 115 healthy controls were enrolled. NOS-based and parameter-weighted connectome matrices were calculated from MRI images obtained with a 3-T MRI unit. With 5-fold cross-validation, diagnostic performance of convolutional neural network (CNN) models using those connectome matrices in differentiating patients with PD from healthy controls was evaluated. To identify the important brain connections for diagnosing PD, gradient-weighted class activation mapping (Grad-CAM) was applied to the trained CNN models. Results CNN models based on some parameter-weighted structural matrices (diffusion kurtosis imaging (DKI)–weighted, neurite orientation dispersion and density imaging (NODDI)–weighted, and g-ratio-weighted connectome matrices) showed moderate performance (areas under the receiver operating characteristic curve (AUCs) = 0.895, 0.801, and 0.836, respectively) in discriminating PD patients from healthy controls. The DKI-weighted connectome matrix performed significantly better than the conventional NOS-based matrix (AUC = 0.761) (DeLong’s test, p < 0.0001). Alterations of neural connections between the basal ganglia and cerebellum were indicated by applying Grad-CAM to the NODDI- and g-ratio-weighted matrices. Conclusion Patients with PD can be differentiated from healthy controls by applying the deep learning technique to the parameter-weighted connectome matrices, and neural circuit disorders including those between the basal ganglia on one side and the cerebellum on the contralateral side were visualized.

scholarly journals Diffusion Kurtosis Imaging of Substantia Nigra Is a Sensitive Method for Early Diagnosis and Disease Evaluation in Parkinson’s Disease

2015 ◽  
Vol 2015 ◽  
pp. 1-5 ◽  
Author(s):  
Guohua Zhang ◽  
Yuhu Zhang ◽  
Chengguo Zhang ◽  
Yukai Wang ◽  
Guixian Ma ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Substantia Nigra ◽  
Rating Scale ◽  
Diffusion Tensor ◽  
Diffusion Kurtosis Imaging ◽  
Healthy Controls ◽  
Potential Biomarker ◽  
Diffusion Kurtosis ◽  
Sensitive Method

Background.To diagnose Parkinson disease (PD) in an early stage and accurately evaluate severity, it is important to develop a sensitive method for detecting structural changes in the substantia nigra (SN).Method.Seventy-two untreated patients with early PD and 72 healthy controls underwent diffusion tensor and diffusion kurtosis imaging. Regions of interest were drawn in the rostral, middle, and caudal SN by two blinded and independent raters. Mean kurtosis (MK) and fractional anisotropy in the SN were compared between the groups. Receiver operating characteristic (ROC) and Spearman correlation analyses were used to compare the diagnostic accuracy and correlate imaging findings with Hoehn-Yahr (H-Y) staging and part III of the Unified Parkinson’s Disease Rating Scale (UPDRS-III).Result.MK in the SN was increased significantly in PD patients compared with healthy controls. The area under the ROC curve was 0.976 for MK in the SN (sensitivity, 0.944; specificity, 0.917). MK in the SN had a positive correlation with H-Y staging and UPDRS-III scores.Conclusion.Diffusion kurtosis imaging is a sensitive method for PD diagnosis and severity evaluation. MK in the SN is a potential biomarker for imaging studies of early PD that can be widely used in clinic.

scholarly journals Visual Impairments Are Associated With Retinal Microvascular Density in Patients With Parkinson’s Disease

2021 ◽  
Vol 15 ◽  
Author(s):  
Min Zhou ◽  
Lei Wu ◽  
Qinyuan Hu ◽  
Congyao Wang ◽  
Jiacheng Ye ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Visual Impairment ◽  
Characteristic Curve ◽  
Microvascular Density ◽  
Inner Plexiform Layer ◽  
Healthy Controls ◽  
Fiber Layer ◽  
P100 Latency ◽  
Retinal Microvasculature

ObjectiveThis study aimed to evaluate retinal microvascular density in patients with Parkinson’s disease (PD) and its correlation with visual impairment.MethodsThis cross-sectional study included 24 eyes of 24 patients with PD and 23 eyes of 23 healthy controls. All participants underwent ophthalmic examination, visual evoked potential (VEP) test, 25-item National Eye Institute Visual Function Questionnaire (NEI VFQ-25), and optical coherence tomography angiography (OCTA) examination. The correlation between retinal microvascular density and visual parameter was evaluated using Spearman correlation analysis, and the area under receiver operating characteristic curve (AUROC) was calculated.ResultsParkinson’s disease patients had prolonged P100 latency (P = 0.041), worse vision-related quality of life (composite score and 3 of 12 subscales in NEI VFQ-25), and decreased vessel density (VD) in all sectors of 3-mm-diameter region (all P &lt; 0.05) compared with healthy controls. There were no statistical differences in the ganglion cell-inner plexiform layer (GCIPL) thickness and retinal nerve fiber layer (RNFL) thickness between the two groups. A negative correlation was found between P100 latency and nasal and superior sectors of macular VD in a 3-mm-diameter region (r = −0.328, P = 0.030; r = −0.302, and P = 0.047, respectively). Macular VD in a 3-mm-diameter region showed diagnostic capacities to distinguish PD patients from healthy controls (AUROCs, ranging from 0.655 to 0.723).ConclusionThis study demonstrated that decreased retinal microvascular density was correlated with visual impairment in PD patients. Retinal microvasculature change may occur earlier than visual decline and retinal structure change and has the potential to be a promising diagnostic marker for early PD.

14 Pathological oscillatory activity in Parkinson’s disease; what does it mean and how should we treat it?

2020 ◽  
Vol 91 (8) ◽  
pp. e6.1-e6
Author(s):  
Peter Brown
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Brain Stimulation ◽  
Basal Ganglia ◽  
Side Effects ◽  
Brain Stimulation ◽  
Neural Circuit ◽  
Symptom Control ◽  
Oscillatory Activity ◽  
Deep Brain

Professor Peter Brown is Professor of Experimental Neurology and Director of the Medical Research Council Brain Network Dynamics Unit at the University of Oxford. Prior to 2010 he was a Professor of Neurology at University College London.For decades we have had cardiac pacemakers that adjust their pacing according to demand and yet therapeutic adaptive stimulation approaches for the central nervous system are still not clinically available. Instead, to treat patients with advanced Parkinson’s disease we stimulate the basal ganglia with fixed regimes, unvarying in frequency or intensity. Although effective, this comes with side-effects and in terms of sophistication this treatment approach could be compared to having central heating system on all the time, regardless of temperature. This talk will describe recent steps being taken to define the underlying circuit dysfunction in Parkinson’s and to improve deep brain stimulation by controlling its delivery according to the state of pathological activity.Evidence is growing that motor symptoms in Parkinson’s disease are due, at least in part, to excessive synchronisation between oscillating neurons. Recordings confirm bursts of oscillatory synchronisation in the basal ganglia centred around 20 Hz. The bursts of 20 Hz activity are prolonged in patients withdrawn from their usual medication and the dominance of these long duration bursts negatively correlates with motor impairment. Longer bursts attain higher amplitudes, indicative of more pervasive oscillatory synchronisation within the neural circuit. In contrast, in heathy primates and in treated Parkinson’s disease bursts tend to be short. Accordingly, it might be best to use closed-loop controlled deep brain stimulation to selectively terminate longer, bigger, pathological beta bursts to both save power and to spare the ability of underlying neural circuits to engage in more physiological processing between long bursts. It is now possible to record and characterise bursts on-line during stimulation of the same site and trial adaptive stimulation. Thus far, this has demonstrated improvements in efficiency and side-effects over conventional continuous stimulation, with at least as good symptom control in Parkinsonian patients.

scholarly journals Convolutional Neural Network Optimize the Application of Diffusion Kurtosis Imaging in Parkinson’s Disease

2021 ◽  
Author(s):  
Junyan Sun ◽  
Ruike Chen ◽  
Qiqi Tong ◽  
Jinghong Ma ◽  
Linlin Gao ◽  
...  
Keyword(s):  
Neural Network ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Model Fitting ◽  
Diffusion Kurtosis Imaging ◽  
Clinical Assessments ◽  
Fitting Method ◽  
Diffusion Kurtosis

Abstract Objectives: This work attempted to assess the feasibility of deep-learning based method in detecting the alterations of diffusion kurtosis measurements associated with Parkinson's disease (PD). Methods: A group of 68 PD patients and 77 healthy controls (HCs) were scanned on the scanner-A (3T Skyra) (DATASET-1). Meanwhile, an additional 5 healthy travelling volunteers were scanned with both the scanner-A and an additional scanner-B (3T Prisma) (DATASET-2). Diffusion kurtosis imaging (DKI) of DATASET-2 has an extra b shell than that of DATASET-1. In addition, a 3D convolutional neural network (CNN) was trained from Dataset 2 to harmonize the quality of scalar measures of scanner-A to a similar level of scanner-B. Whole-brain unpaired t-test and Tract-Based Spatial Statistics (TBSS) was performed to validate the differences between PD and control groups with model fitting method and CNN method respectively. We further clarified the correlation between clinical assessments and DKI results.Results: In the left substantia nigra (SN), an increase of mean diffusivity (MD) was found in PD group. In the right SN, fractional anisotropy (FA) and mean kurtosis (MK) values were negatively correlated with Hoehn & Yahr (H&Y) scales. In the putamen, FA values was positively correlated with H&Y scales. It is worth noting that, these findings were only observed with the deep-learning method. There was neither group difference, nor correlation with clinical assessments in the SN or striatum exceeding the significant level by using the conventional model fitting method.Conclusions: CNN method improves the robustness of DKI and can help to explore PD-associated imaging features.

scholarly journals Soluble Triggering Receptor Expressed on Myeloid Cells 2 From Cerebrospinal Fluid in Sleep Disorders Related to Parkinson’s Disease

2021 ◽  
Vol 13 ◽  
Author(s):  
Mingshu Mo ◽  
Yuting Tang ◽  
Lijian Wei ◽  
Jiewen Qiu ◽  
Guoyou Peng ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Sleep Disorders ◽  
Characteristic Curve ◽  
Myeloid Cells ◽  
Diagnostic Value ◽  
Healthy Controls ◽  
Potential Biomarker ◽  
The Central Nervous System ◽  
The Relationship

Background: Triggering receptor expressed on myeloid cells 2 (TREM2) is a microglial receptor exclusively expressed in the central nervous system (CNS). It contributes to abnormal protein aggregation in neurodegenerative disorders, but its role in Parkinson’s disease (PD) is still unclear.Methods: In this case-control study, we measured the concentration of the soluble fragment of TREM2 (sTREM2) in PD patients, evaluated their sleep conditions by the PD sleep scale (PDSS), and analyzed the relationship between sTREM2 and PD symptoms.Results: We recruited 80 sporadic PD patients and 65 healthy controls without disease-related variants in TREM2. The concentration of sTREM2 in the CSF was significantly higher in PD patients than in healthy controls (p &lt; 0.01). In the PD group, the concentration of sTREM2 had a positive correlation with α-syn in the CSF (Pearson r = 0.248, p = 0.027). Receiver operating characteristic curve (ROC) analyses showed that sTREM2 in the CSF had a significant diagnostic value for PD (AUC, 0.791; 95% CI, 0.711–0.871, p &lt; 0.05). The subgroup analysis showed that PD patients with sleep disorders had a significantly higher concentration of sTREM2 in their CSF (p &lt; 0.01). The concentration of sTREM2 in the CSF had a negative correlation with the PDSS score in PD patients (Pearson r = −0.555, p &lt; 0.01). The ROC analyses showed that sTREM2 in the CSF had a significant diagnostic value for sleep disorders in PD (AUC, 0.733; 95% CI, 0.619–0.846, p &lt; 0.05).Conclusion: Our findings suggest that CSF sTREM2 may be a potential biomarker for PD and it could help predict sleep disorders in PD patients, but multicenter prospective studies with more participants are still needed to confirm its diagnostic value in future.

scholarly journals Convolutional neural network optimizes the application of diffusion kurtosis imaging in Parkinson’s disease

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Junyan Sun ◽  
Ruike Chen ◽  
Qiqi Tong ◽  
Jinghong Ma ◽  
Linlin Gao ◽  
...  
Keyword(s):  
Neural Network ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Model Fitting ◽  
Diffusion Kurtosis Imaging ◽  
Clinical Assessments ◽  
Fitting Method ◽  
Diffusion Kurtosis

Abstract Objectives The literature regarding the use of diffusion-tensor imaging-derived metrics in the evaluation of Parkinson’s disease (PD) is controversial. This study attempted to assess the feasibility of a deep-learning-based method for detecting alterations in diffusion kurtosis measurements associated with PD. Methods A total of 68 patients with PD and 77 healthy controls were scanned using scanner-A (3 T Skyra) (DATASET-1). Meanwhile, an additional five healthy volunteers were scanned with both scanner-A and an additional scanner-B (3 T Prisma) (DATASET-2). Diffusion kurtosis imaging (DKI) of DATASET-2 had an extra b shell compared to DATASET-1. In addition, a 3D-convolutional neural network (CNN) was trained from DATASET-2 to harmonize the quality of scalar measures of scanner-A to a similar level as scanner-B. Whole-brain unpaired t test and Tract-Based Spatial Statistics (TBSS) were performed to validate the differences between the PD and control groups using the model-fitting method and CNN-based method, respectively. We further clarified the correlation between clinical assessments and DKI results. Results An increase in mean diffusivity (MD) was found in the left substantia nigra (SN) in the PD group. In the right SN, fractional anisotropy (FA) and mean kurtosis (MK) values were negatively correlated with Hoehn and Yahr (H&Y) scales. In the putamen (Put), FA values were positively correlated with the H&Y scales. It is worth noting that these findings were only observed with the deep learning method. There was neither a group difference nor a correlation with clinical assessments in the SN or striatum exceeding the significance level using the conventional model-fitting method. Conclusions The CNN-based method improves the robustness of DKI and can help to explore PD-associated imaging features.

scholarly journals Deep learning and automated Cell Painting reveal Parkinson’s disease-specific signatures in primary patient fibroblasts

2020 ◽  
Author(s):  
Lauren Schiff ◽  
Bianca Migliori ◽  
Ye Chen ◽  
Deidre Carter ◽  
Caitlyn Bonilla ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Deep Learning ◽  
Specific Cell ◽  
High Fidelity ◽  
Healthy Controls ◽  
Cell Models ◽  
Disease Phenotypes ◽  
Primary Fibroblasts ◽  
Disease Specific

Drug discovery for Parkinson’s disease (PD) is impeded by the lack of screenable phenotypes in scalable cell models. Here we present a novel unbiased phenotypic profiling platform that combines automation, Cell Painting, and deep learning. We applied this platform to primary fibroblasts from 91 PD patients and carefully matched healthy controls, generating the largest publicly available Cell Painting dataset to date. Using fixed weights from a convolutional deep neural network trained on ImageNet, we generated unbiased deep embeddings from each image, and applied these to train machine learning models to detect morphological disease phenotypes. Interestingly, our models captured individual variation by identifying specific cell lines within the cohort with high fidelity, even across different batches and plate layouts, demonstrating platform robustness and sensitivity. Importantly, our models were able to confidently separate LRRK2 and sporadic PD lines from healthy controls (ROC AUC 0.79 (0.08 standard deviation (SD))) supporting the capacity of this platform for PD modeling and drug screening applications.

Sign in / Sign up

Export Citation Format

Share Document